{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":4,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":4,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"3a76d6254d98","filters":{"venue":"ACM Transactions on Speech and Language Processing"}},"results":[{"id":"W2109163800","doi":"10.1145/1187415.1187417","title":"A statistical model for near-synonym choice","year":2007,"lang":"en","type":"article","venue":"ACM Transactions on Speech and Language Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Synonym (taxonomy); Artificial intelligence; Natural language processing; Task (project management); Context (archaeology); Machine translation; Thesaurus; Mutual information; Information retrieval; Machine learning","authors":[{"name":"Diana Inkpen","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01971804255985616,"gpt":0.3185797563200914,"spread":0.2988617137602353,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007710207,0.0008869519,0.001535097,0.004647051,0.001216191,0.002365637,0.003732417,0.002097383,0.006610387],"category_scores_gemma":[0.02908325,0.0009377501,0.001802021,0.004780365,0.002132369,0.006543473,0.002222133,0.003029281,0.002916869],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001451034,"about_ca_system_score_gemma":0.001957068,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00510651,"about_ca_topic_score_gemma":0.008466461,"domain_scores_codex":[0.9942364,0.002718104,0.0003914164,0.001274879,0.001098008,0.0002813216],"domain_scores_gemma":[0.9796816,0.01514949,0.001525214,0.001619487,0.001658699,0.0003654337],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005407126,0.0005336883,0.01318171,0.0003272263,0.0006339837,0.0007943607,0.0009751529,0.3685607,0.006033978,0.3656934,0.01271676,0.2300084],"study_design_scores_gemma":[0.00002678683,0.00004102195,0.0008477432,0.00001400667,0.00002549104,0.0001286284,0.00002777371,0.8600659,0.0004930675,0.136903,0.001387926,0.00003872755],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01697694,0.000212936,0.9791524,0.000506069,0.00006433646,0.00009699557,0.0004963054,0.0005595031,0.001934551],"genre_scores_gemma":[0.5934439,0.0005410455,0.3913545,0.000535332,0.0004672578,0.001017406,0.002852882,0.0005227919,0.00926476],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007710207,"threshold_uncertainty_score":0.04077595,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2091014931","doi":"10.1145/1177055.1177057","title":"Confidence estimation for NLP applications","year":2006,"lang":"en","type":"article","venue":"ACM Transactions on Speech and Language Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada; Université de Montréal","funders":"","keywords":"Computer science; Machine translation; Artificial intelligence; Natural language processing; Estimation; Confidence interval; Natural language; Machine learning; Statistics; Mathematics","authors":[{"name":"Simona Gandrabur","is_ca":true},{"name":"George Foster","is_ca":true},{"name":"Guy Lapalme","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.00987436474930131,"gpt":0.2842979056426198,"spread":0.2744235408933184,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0166974,0.001399912,0.001844465,0.005294047,0.0012853,0.005421385,0.00334534,0.003020306,0.007403893],"category_scores_gemma":[0.2205581,0.00100757,0.001283321,0.004816669,0.002120306,0.007606319,0.004191077,0.004928445,0.003392886],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001413335,"about_ca_system_score_gemma":0.001741208,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002366609,"about_ca_topic_score_gemma":0.001089834,"domain_scores_codex":[0.9736894,0.01161834,0.002234871,0.003222605,0.008601945,0.0006328522],"domain_scores_gemma":[0.8360274,0.1337048,0.00566833,0.01080912,0.01284312,0.0009473805],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004909163,0.0001440298,0.006720331,0.001248772,0.0002420924,0.0004877081,0.0005619212,0.1210634,0.005415148,0.2522609,0.02006124,0.5913035],"study_design_scores_gemma":[0.00004395898,0.00008241483,0.001354968,0.0002405878,0.0000555381,0.0004213444,0.0001046754,0.650025,0.006666863,0.3240908,0.01683585,0.00007799829],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002372802,0.001089597,0.9924812,0.0004443128,0.00007542683,0.00005790106,0.0002662093,0.001150586,0.002061976],"genre_scores_gemma":[0.3284656,0.002281546,0.6604008,0.0007382846,0.001019223,0.0006410613,0.002448832,0.001191807,0.002812807],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0166974,"threshold_uncertainty_score":0.08830529,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2130998770","doi":"10.1145/1596517.1596518","title":"Extrinsic summarization evaluation","year":2009,"lang":"en","type":"article","venue":"ACM Transactions on Speech and Language Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Sixth Framework Programme","keywords":"Automatic summarization; Computer science; Task (project management); Information retrieval; Audit; Human–computer interaction; Natural language processing; Artificial intelligence","authors":[{"name":"Gabriel Murray","is_ca":true},{"name":"Thomas Kleinbauer","is_ca":false},{"name":"Peter Poller","is_ca":false},{"name":"Tilman Becker","is_ca":false},{"name":"Steve Renals","is_ca":false},{"name":"Jonathan Kilgour","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02421893031646663,"gpt":0.2929102533355549,"spread":0.2686913230190883,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01229399,0.002190424,0.001283905,0.003015913,0.0008337756,0.00304517,0.001674084,0.00145449,0.01009868],"category_scores_gemma":[0.06587509,0.0002529407,0.0008075855,0.001603739,0.0005683884,0.003067926,0.001836114,0.00110242,0.00411756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008043082,"about_ca_system_score_gemma":0.0008347191,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008024478,"about_ca_topic_score_gemma":0.001114742,"domain_scores_codex":[0.9779556,0.01101388,0.002280524,0.001879535,0.006419891,0.000450543],"domain_scores_gemma":[0.9409888,0.0279407,0.003325114,0.005820352,0.02104724,0.0008779025],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003788558,0.0008779663,0.009817999,0.003564328,0.000605443,0.0004358901,0.0009977736,0.01473072,0.06241746,0.003241143,0.03960078,0.859922],"study_design_scores_gemma":[0.001037001,0.009488849,0.0650547,0.0007347289,0.001635269,0.003004554,0.002959047,0.4277896,0.289561,0.009641589,0.1883651,0.0007285698],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2800617,0.005843942,0.6303888,0.001201964,0.001438467,0.003749424,0.0135761,0.02590509,0.03783436],"genre_scores_gemma":[0.6657206,0.001349329,0.2719752,0.0006516043,0.000780337,0.002088147,0.03493344,0.002982893,0.01951849],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01229399,"threshold_uncertainty_score":0.06501764,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2052227241","doi":"10.1145/1289600.1289602","title":"Adaptive text correction with Web-crawled domain-dependent dictionaries","year":2007,"lang":"en","type":"article","venue":"ACM Transactions on Speech and Language Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Trigram; Vocabulary; Natural language processing; Domain (mathematical analysis); Information retrieval; Word (group theory); Artificial intelligence; Web page; Crawling; Punctuation; Linguistics; World Wide Web","authors":[{"name":"Christoph Ringlstetter","is_ca":true},{"name":"Klaus U. Schulz","is_ca":false},{"name":"Stoyan Mihov","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.008003122257323006,"gpt":0.25074320704803,"spread":0.2427400847907071,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001528184,0.001217148,0.001257423,0.003146449,0.000654217,0.001217049,0.001362612,0.0008773308,0.001766398],"category_scores_gemma":[0.02153648,0.000702237,0.000598648,0.002912188,0.0005772642,0.002558507,0.00148824,0.001021871,0.002889173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004148117,"about_ca_system_score_gemma":0.001140989,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004798142,"about_ca_topic_score_gemma":0.0073139,"domain_scores_codex":[0.9979928,0.0006028052,0.0002432243,0.0005223465,0.0005574821,0.00008143405],"domain_scores_gemma":[0.9814299,0.008723803,0.001101576,0.005027774,0.003455435,0.000261412],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007466272,0.0007396204,0.01350457,0.0009826246,0.0002695053,0.0007490371,0.001371365,0.02896707,0.09859189,0.001854209,0.01249772,0.8397259],"study_design_scores_gemma":[0.000277876,0.0006226463,0.01274206,0.0001275724,0.0003289746,0.001674297,0.0008417614,0.6800956,0.2670591,0.003618448,0.03242031,0.000191492],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2529732,0.001184369,0.6590394,0.0003326262,0.000270491,0.0008032728,0.002017205,0.07972155,0.003657857],"genre_scores_gemma":[0.3005859,0.0005381117,0.6807449,0.0001924931,0.00007964262,0.000465995,0.006483802,0.003689079,0.007220119],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004798142,"threshold_uncertainty_score":0.009540439,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}